INDEX

Explanations

words related to television ratings

oai_token-act-pair · gpt-3.5-turbo

references to television ratings

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Alz

-0.87

working

-0.76

 Fathers

-0.70

vas

-0.67

 Remem

-0.67

 Marse

-0.67

 Gibbs

-0.65

forth

-0.65

cise

-0.65

adr

-0.64

POSITIVE LOGITS

 ratings

1.41

 rating

1.23

 Ratings

1.18

 Rating

0.95

 rated

0.92

 veter

0.91

 coefficients

0.83

omial

0.82

olitan

0.80

Rating

0.78

Activations Density 0.007%

words related to television ratings

references to television ratings

No Comments

No Known Activations